Methods and apparatus for retrieving images from a large collection of images
    1.
    发明授权
    Methods and apparatus for retrieving images from a large collection of images 有权
    从大量图像中检索图像的方法和装置

    公开(公告)号:US08200027B2

    公开(公告)日:2012-06-12

    申请号:US12952923

    申请日:2010-11-23

    IPC分类号: G06K9/62

    摘要: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.

    摘要翻译: 图像检索程序(IRP)可用于查询数字图像的集合。 IRP可以包括挖掘模块,以使用本地和全局特征描述符来相对于用户选择的积极示例的相似度来自动地对集合中的数字图像进行排序。 每个局部特征描述符可以基于将该图像划分成多个部分来表示图像的一部分。 每个全局特征描述符可以表示整个图像。 IRP的用户界面模块可以接收标识图像的输入作为正例。 基于挖掘模块的结果,用户界面模块还可以根据与正面示例的相似性的排序顺序在用户界面中从集合中呈现图像。 查询概念可能被保存和重用。 描述和要求保护其他实施例。

    Methods and apparatus for retrieving images from a large collection of images
    2.
    发明申请
    Methods and apparatus for retrieving images from a large collection of images 有权
    从大量图像中检索图像的方法和装置

    公开(公告)号:US20080118151A1

    公开(公告)日:2008-05-22

    申请号:US11604114

    申请日:2006-11-22

    IPC分类号: G06K9/00

    摘要: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.

    摘要翻译: 图像检索程序(IRP)可用于查询数字图像的集合。 IRP可以包括挖掘模块,以使用本地和全局特征描述符来相对于用户选择的积极示例的相似度来自动地对集合中的数字图像进行排序。 每个局部特征描述符可以基于将该图像划分成多个部分来表示图像的一部分。 每个全局特征描述符可以表示整个图像。 IRP的用户界面模块可以接收标识图像的输入作为正例。 基于挖掘模块的结果,用户界面模块还可以根据与正面示例的相似性的排序顺序在用户界面中从集合中呈现图像。 查询概念可能被保存和重用。 描述和要求保护其他实施例。

    METHODS AND APPARATUS FOR RETRIEVING IMAGES FROM A LARGE COLLECTION OF IMAGES
    3.
    发明申请
    METHODS AND APPARATUS FOR RETRIEVING IMAGES FROM A LARGE COLLECTION OF IMAGES 有权
    用于从大量图像中检索图像的方法和装置

    公开(公告)号:US20110081090A1

    公开(公告)日:2011-04-07

    申请号:US12952923

    申请日:2010-11-23

    IPC分类号: G06K9/62

    摘要: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.

    摘要翻译: 图像检索程序(IRP)可用于查询数字图像的集合。 IRP可以包括挖掘模块,以使用本地和全局特征描述符来相对于用户选择的积极示例的相似度来自动地对集合中的数字图像进行排序。 每个局部特征描述符可以基于将该图像划分成多个部分来表示图像的一部分。 每个全局特征描述符可以表示整个图像。 IRP的用户界面模块可以接收标识图像的输入作为正例。 基于挖掘模块的结果,用户界面模块还可以根据与正面示例的相似性的排序顺序在用户界面中从集合中呈现图像。 查询概念可能被保存和重用。 描述和要求保护其他实施例。

    METHODS AND APPARATUS FOR RETRIEVING IMAGES FROM A LARGE COLLECTION OF IMAGES
    4.
    发明申请
    METHODS AND APPARATUS FOR RETRIEVING IMAGES FROM A LARGE COLLECTION OF IMAGES 有权
    用于从大量图像中检索图像的方法和装置

    公开(公告)号:US20120173549A1

    公开(公告)日:2012-07-05

    申请号:US13421406

    申请日:2012-03-15

    IPC分类号: G06F17/30

    摘要: A processing system may receive an example image for use in querying a collection of digital images. The processing system may use local and global feature descriptors to perform a content-based image comparison of the digital images with the example image, to automatically rank the digital images with respect to similarity to the example image. A local feature descriptor may represent a portion of the contents of a digital image. A global feature descriptor may represent substantially all of the contents of that digital image. The global feature descriptor may be content based, not keyword based. Intermediate and final classifiers may be used to perform the automatic ranking. Different intermediate classifiers may generate intermediate relevance metrics with respect to different modalities. The final classifier may use results from the intermediate classifiers to produce a final relevance metric for the digital images. Other embodiments are described and claimed.

    摘要翻译: 处理系统可以接收用于查询数字图像集合的示例图像。 处理系统可以使用本地和全局特征描述符来执行数字图像与示例图像的基于内容的图像比较,以便根据与示例图像的相似度对数字图像进行自动排序。 局部特征描述符可以表示数字图像内容的一部分。 全局特征描述符可以基本上代表该数字图像的所有内容。 全局特征描述符可以是基于内容的,而不是基于关键字。 中级和最终分类器可用于执行自动排序。 不同的中间分类器可以产生关于不同模态的中间相关性度量。 最终分类器可以使用来自中间分类器的结果来产生数字图像的最终相关性度量。 描述和要求保护其他实施例。

    Methods and apparatus for retrieving images from a large collection of images
    5.
    发明授权
    Methods and apparatus for retrieving images from a large collection of images 有权
    从大量图像中检索图像的方法和装置

    公开(公告)号:US07840076B2

    公开(公告)日:2010-11-23

    申请号:US11604114

    申请日:2006-11-22

    IPC分类号: G06K9/62

    摘要: An image retrieval program (IRP) may be used to query a collection of digital images. The IRP may include a mining module to use local and global feature descriptors to automatically rank the digital images in the collection with respect to similarity to a user-selected positive example. Each local feature descriptor may represent a portion of an image based on a division of that image into multiple portions. Each global feature descriptor may represent an image as a whole. A user interface module of the IRP may receive input that identifies an image as the positive example. The user interface module may also present images from the collection in a user interface in a ranked order with respect to similarity to the positive example, based on results of the mining module. Query concepts may be saved and reused. Other embodiments are described and claimed.

    摘要翻译: 图像检索程序(IRP)可用于查询数字图像的集合。 IRP可以包括挖掘模块,以使用本地和全局特征描述符来相对于用户选择的积极示例的相似度来自动地对集合中的数字图像进行排序。 每个局部特征描述符可以基于将该图像划分成多个部分来表示图像的一部分。 每个全局特征描述符可以表示整个图像。 IRP的用户界面模块可以接收标识图像的输入作为正例。 基于挖掘模块的结果,用户界面模块还可以根据与正面示例的相似性的排序顺序在用户界面中从集合中呈现图像。 查询概念可能被保存和重用。 描述和要求保护其他实施例。

    Methods and apparatus for retrieving images from a large collection of images
    6.
    发明授权
    Methods and apparatus for retrieving images from a large collection of images 有权
    从大量图像中检索图像的方法和装置

    公开(公告)号:US08565537B2

    公开(公告)日:2013-10-22

    申请号:US13421406

    申请日:2012-03-15

    IPC分类号: G06K9/62

    摘要: A processing system may receive an example image for use in querying a collection of digital images. The processing system may use local and global feature descriptors to perform a content-based image comparison of the digital images with the example image, to automatically rank the digital images with respect to similarity to the example image. A local feature descriptor may represent a portion of the contents of a digital image. A global feature descriptor may represent substantially all of the contents of that digital image. The global feature descriptor may be content based, not keyword based. Intermediate and final classifiers may be used to perform the automatic ranking. Different intermediate classifiers may generate intermediate relevance metrics with respect to different modalities. The final classifier may use results from the intermediate classifiers to produce a final relevance metric for the digital images. Other embodiments are described and claimed.

    摘要翻译: 处理系统可以接收用于查询数字图像集合的示例图像。 处理系统可以使用本地和全局特征描述符来执行数字图像与示例图像的基于内容的图像比较,以便根据与示例图像的相似度对数字图像进行自动排序。 局部特征描述符可以表示数字图像内容的一部分。 全局特征描述符可以基本上代表该数字图像的所有内容。 全局特征描述符可以是基于内容的,而不是基于关键字。 中级和最终分类器可用于执行自动排序。 不同的中间分类器可以产生关于不同模态的中间相关性度量。 最终分类器可以使用来自中间分类器的结果来产生数字图像的最终相关性度量。 描述和要求保护其他实施例。

    Methods and apparatus to analyze processor systems
    7.
    发明申请
    Methods and apparatus to analyze processor systems 有权
    分析处理器系统的方法和装置

    公开(公告)号:US20070157177A1

    公开(公告)日:2007-07-05

    申请号:US11323532

    申请日:2005-12-30

    IPC分类号: G06F9/44

    摘要: Methods and apparatus are disclosed to analyze processor system. An example method to analyze execution of a multi-threaded program on a processor system includes generating a first program trace associated with the execution of a first thread, generating a first list of execution frequencies associated with the first program trace, generating a second program trace associated with the execution of a second thread, generating a second list of execution frequencies associated with the second trace, generating a first set of one or more vectors for the first list of execution frequencies, generating a second set of one or more vectors for the second list of execution frequencies, and analyzing the one or more vectors to identify one or more program phases.

    摘要翻译: 公开了分析处理器系统的方法和装置。 分析处理器系统上的多线程程序的执行的示例性方法包括生成与第一线程的执行相关联的第一程序跟踪,生成与第一程序跟踪相关联的执行频率的第一列表,生成第二程序跟踪 与第二线程的执行相关联,生成与第二跟踪相关联的执行频率的第二列表,为第一执行频率列表生成第一组一个或多个向量,生成用于该第一线索的一个或多个向量的第二组, 执行频率的第二列表,以及分析所述一个或多个向量以识别一个或多个程序阶段。

    Methods and apparatus to analyze processor systems
    8.
    发明授权
    Methods and apparatus to analyze processor systems 有权
    分析处理器系统的方法和装置

    公开(公告)号:US07739662B2

    公开(公告)日:2010-06-15

    申请号:US11323532

    申请日:2005-12-30

    IPC分类号: G06F9/44 G06F9/45 G06F11/00

    摘要: Methods and apparatus are disclosed to analyze processor system. An example method to analyze execution of a multi-threaded program on a processor system includes generating a first program trace associated with the execution of a first thread, generating a first list of execution frequencies associated with the first program trace, generating a second program trace associated with the execution of a second thread, generating a second list of execution frequencies associated with the second trace, generating a first set of one or more vectors for the first list of execution frequencies, generating a second set of one or more vectors for the second list of execution frequencies, and analyzing the one or more vectors to identify one or more program phases.

    摘要翻译: 公开了分析处理器系统的方法和装置。 分析处理器系统上的多线程程序的执行的示例性方法包括生成与第一线程的执行相关联的第一程序跟踪,生成与第一程序跟踪相关联的执行频率的第一列表,生成第二程序跟踪 与第二线程的执行相关联,生成与第二跟踪相关联的执行频率的第二列表,为第一执行频率列表生成第一组一个或多个向量,生成用于该第一线索的一个或多个向量的第二组, 执行频率的第二列表,以及分析所述一个或多个向量以识别一个或多个程序阶段。